Skip to main navigation Skip to search Skip to main content

Context-Gloss Augmentation for Improving Arabic Target Sense Verification

  • Birzeit University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Arabic language lacks semantic datasets and sense inventories. The most common semantically-labeled dataset for Arabic is the ArabGlossBERT, a relatively small dataset that consists of 167K context-gloss pairs (about 60K positive and 107K negative pairs), collected from Arabic dictionaries. This paper presents an enrichment to the ArabGlossBERT dataset, by augmenting it using (Arabic-English-Arabic) machine back-translation. Augmentation increased the dataset size to 352K pairs (149K positive and 203K negative pairs). We measure the impact of augmentation using different data configurations to fine-tune BERT on target sense verification (TSV) task. Overall, the accuracy ranges between 78% to 84% for different data configurations. Although our approach performed at par with the baseline, we did observe some improvements for some POS tags in some experiments. Furthermore, our fine-tuned models are trained on a larger dataset covering larger vocabulary and contexts. We provide an in-depth analysis of the accuracy for each part-of-speech (POS).

Original languageEnglish
Title of host publication12th Global Wordnet Conference, GWC 2023
EditorsGerman Rigau, Francis Bond, Alexandre Rademaker
PublisherAssociation for Computational Linguistics (ACL)
Pages254-262
Number of pages9
ISBN (Electronic)9781713890881
Publication statusPublished - 27 Jan 2023
Externally publishedYes
Event12th Global Wordnet Conference, GWC 2023 - Donositia-San Sebastian, Spain
Duration: 23 Jan 202327 Jan 2023

Publication series

Name12th Global Wordnet Conference, GWC 2023

Conference

Conference12th Global Wordnet Conference, GWC 2023
Country/TerritorySpain
CityDonositia-San Sebastian
Period23/01/2327/01/23

Fingerprint

Dive into the research topics of 'Context-Gloss Augmentation for Improving Arabic Target Sense Verification'. Together they form a unique fingerprint.

Cite this